Artificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Generating music is very difficult; components like long and short term structure present time complexity, which can be difficult for neural networks to capture. Additionally, the acoustics of musical features like harmonies and chords, as well as timbre and instrumentation require complex representations for a network to accurately generate them. Various techniques for both music representation and network architecture have been used in the past decade to address these challenges in music generation. The focus of this thesis extends beyond generating music to the challenge of controlling and/or conditioning that generation. Conditional generation involves an additional piece or pieces of information which are input to the generator and constrain aspects of the results. Conditioning can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored. This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact of this conditioning on the generated music. / Master of Science / Artificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Beyond simply generating music lies the challenge of controlling or conditioning that generation. Conditional generation can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored, especially for generative adversarial networks (GANs). This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact and effectiveness of this conditioning on the generated music.

Mark-recapture methods use repeated captures of individually identifiable animals to provide estimates of properties of populations. Different models allow estimates to be obtained for population size and rates of processes governing population dynamics. State-space models consist of two linked processes evolving simultaneously over time. The state process models the evolution of the true, but unknown, states of the population. The observation process relates observations on the population to these true states. Mark-recapture models specified within a state-space framework allow population dynamics models to be embedded in inference ensuring that estimated changes in the population are consistent with assumptions regarding the biology of the modelled population. This overcomes a limitation of current mark-recapture methods. Two alternative approaches are considered. The "conditional" approach conditions on known numbers of animals possessing capture history patterns including capture in the current time period. An animal's capture history determines its state; consequently, capture parameters appear in the state process rather than the observation process. There is no observation error in the model. Uncertainty occurs only through the numbers of animals not captured in the current time period. An "unconditional" approach is considered in which the capture histories are regarded as observations. Consequently, capture histories do not influence an animal's state and capture probability parameters appear in the observation process. Capture histories are considered a random realization of the stochastic observation process. This is more consistent with traditional mark-recapture methods. Development and implementation of particle filtering techniques for fitting these models under each approach are discussed. Simulation studies show reasonable performance for the unconditional approach and highlight problems with the conditional approach. Strengths and limitations of each approach are outlined, with reference to Soay sheep data analysis, and suggestions are presented for future analyses.

To predict and anticipate future outcomes or reason about missing information in a sequence is a key ability for agents to be able to make intelligent decisions. This requires strong temporally coherent generative capabilities. Diffusion models have shown huge success in several generative tasks lately, but have not been extensively explored in the video domain. We present Random-Mask Video Diffusion (RaMViD), which extends image diffusion models to videos using 3D convolutions, and introduces a new conditioning technique during training. By varying the mask we condition on, the model is able to perform video prediction, infilling and upsampling. Since we do not use concatenation to condition on a mask, as done in most conditionally trained diffusion models, we are able to utilize the same architecture as used for unconditional training which allows us to train the model in a conditional and unconditional fashion at the same time. We evaluated the model on two benchmark datasets for video prediction, on which we achieve state-of-the-art results, and one for video generation. / Att förutse framtida resultat eller resonera kring bristande information i en sekvens är en viktig förutsättning för agenter att göra intelligenta beslut. Detta kräver robusta temporärt koherenta generativa kapaciteter. Diffusionsmodeller har visat pa stor framgang i flera generativa uppgifter i närtid, men denna potential har inte utforskats grundligt i samband med video. Vi presenterar Random-Mask Video Diffusion (RaMViD), vilket bredar bilddiffusionsmodeller till video med hjälp av 3D konvolutioner, och introducerar en ny konditioneringsteknik under träning. Genom att variera masken vi tränar med kan modellen utföra videoförutsägelse och videoifyllnad. Eftersom vi inte använder konkatenering för att träna pa en mask, som görs i de flesta villkorstränade diffusionsmodeller, har vi möjlighet att använda samma arkiktektur som används för ovillkorad träning, vilket i sin tur tillater oss att träna modellen pa ett villkorat och ovillkorat sätt samtidigt. Vi utvärderade modellen pa tva benchmnark datasets för videoförutsägelse och en för videogenerering, varav pa den första vi uppnade de bästa kvantitativa resultaten bland samtida metoder.

Humans' incredible capacity to model the complexity of the physical world is possible because they cast this complexity as the composition of simpler entities and rules to process them. Extensive work in cognitive science indeed shows that human perception and reasoning ability is structured around objects. Motivated by this observation, a growing number of recent work focused on entity-centric approaches to learning representation and their potential to facilitate downstream tasks. In the first contribution, we show how an entity-centric approach to learning a transition model allows us to extract meaningful visual entities and to learn transition rules that achieve better compositional generalization. In the second contribution, we show how an entity-centric approach to generating graphs allows us to design a model for conditional graph generation that permits direct optimisation of the graph properties. We investigate the performance of our model in a prototype-based molecular graph generation task. In this task, called lead optimization in drug discovery, we wish to adjust a few physico-chemical properties of a molecule that has proven efficient in vitro in order to make a drug out of it. / L'incroyable capacité des humains à modéliser la complexité du monde physique est rendue possible par la décomposition qu'ils en font en un ensemble d'entités et de règles simples. De nombreux travaux en sciences cognitives montre que la perception humaine et sa capacité à raisonner est essentiellement centrée sur la notion d'objet. Motivés par cette observation, de récents travaux se sont intéressés aux différentes approches d'apprentissage de représentations centrées sur des entités et comment ces représentations peuvent être utilisées pour résoudre plus facilement des tâches sous-jacentes. Dans la première contribution on montre comment une architecture centrée sur la notion d'entité va permettre d'extraire des entités visuelles interpretables et d'apprendre un modèle du monde plus robuste aux différentes configurations d'objets. Dans la deuxième contribution on s’intéresse à un modèle de génération de graphes dont l'architecture est également centrée sur la notion d'entités et comment cette architecture rend plus facile l'apprentissage d'une génération conditionelle à certaines propriétés du graphe. On s’intéresse plus particulièrement aux applications en découverte de médicaments. Dans cette tâche, on souhaite optimiser certaines propriétés physico-chmiques du graphe d'une molécule qui a été efficace in-vitro et dont on veut faire un médicament.

The topic of this thesis is the detoxification of language in social networks with a particular focus on style transfer techniques that combine deep learning and linguistic resources. In today’s digital landscape, social networks are rife with communication that can often be toxic, either intentionally or unintentionally. Given the pervasiveness of social media and the potential for toxic language to perpetuate negativity and polarization, this study addresses the problem of toxic language and its transformation into more neutral expressions. The importance of this issue is underscored by the need to promote non-toxic communication in the social networks that are an integral part of modern society. The complexity of natural language and the subtleties of what constitutes toxicity make this a challenging problem worthy of study. To address this problem, this research proposes two models, LexiconGST and MultiLexiconGST, developed based on the Delete&Generate framework. These models integrate linguistic resources into the detoxification system to guide deep learning techniques. Experimental results show that the proposed models perform commendably in the detoxification task compared to stateof-the-art methods. The integration of linguistic resources with deep learning techniques is confirmed to improve the performance of detoxification systems. Finally, this research has implications for social media platforms and online communities, which can now implement more effective moderation tools to promote non-toxic communication. It also opens lines of further research to generalize our proposed method to other text styles. / Ämnet för denna avhandling är avgiftning av språk i sociala nätverk med särskilt fokus på stilöverföringstekniker som kombinerar djupinlärning och språkliga resurser. I dagens digitala landskap är sociala nätverk fulla av kommunikation som ofta kan vara giftig, antingen avsiktligt eller oavsiktligt. Med tanke på hur utbredda sociala medier är och hur giftigt språk kan bidra till negativitet och polarisering, tar den här studien upp problemet med giftigt språk och hur det kan omvandlas till mer neutrala uttryck. Vikten av denna fråga understryks av behovet av att främja giftfri kommunikation i de sociala nätverk som är en integrerad del av det moderna samhället. Komplexiteten i naturligt språk och de subtila aspekterna av vad som utgör toxicitet gör detta till ett utmanande problem som är värt att studera. För att ta itu med detta problem föreslår denna forskning två modeller, LexiconGST och MultiLexiconGST, som utvecklats baserat på ramverket Delete&Generate. Dessa modeller integrerar språkliga resurser i avgiftningssystemet för att vägleda djupinlärningstekniker. Experimentella resultat visar att de föreslagna modellerna presterar lovvärt i avgiftningsuppgiften jämfört med toppmoderna metoder. Integrationen av språkliga resurser med djupinlärningstekniker bekräftas för att förbättra prestanda för avgiftningssystem. Slutligen har denna forskning konsekvenser för sociala medieplattformar och onlinegemenskaper, som nu kan implementera mer effektiva modereringsverktyg för att främja giftfri kommunikation. Det öppnar också för ytterligare forskning för att generalisera vår föreslagna metod till andra textstilar.