Aller au contenu principal
Profil bibliographique

Fatima Tuz Zohora

Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.

23Publications signalées
190Citations signalées
2Affiliations récentes

Les institutions déclarées

Les domaines associés

Advanced Memory and Neural ComputingFerroelectric and Negative Capacitance DevicesDomain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsGender, Labor, and Family Dynamics

Les publications récentes

Accès ouvert 2026 conference-paper OpenAlex

Prototype Replay for Cold-Start Online Class-Incremental Learning in Spiking Networks

Fatima Tuz Zohora, Dhireesha Kudithipudi

Online class-incremental learning is a challenging setting in which the model continually learns new classes from a single pass over the data while retaining discrimination among previously seen classes. Although exemplar replay performs well in this setting, it incurs substantial memory and …

us (code pays fourni par la source)

0 citations
Accès ouvert 2025 article OpenAlex

The neurobench framework for benchmarking neuromorphic computing algorithms and systems

Jason Yik, Korneel Van den Berghe, Douwe den Blanken, Younes Bouhadjar et autres

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future …

us, nl, de, se, hk, it, ch, au, gb, ca, fr, es, kr, be (code pays fourni par la source)

90 citations Nature Communications
Accès ouvert 2024 article OpenAlex

Probabilistic metaplasticity for continual learning with memristors in spiking networks

Fatima Tuz Zohora, Vedant Karia, Nicholas Soures, Dhireesha Kudithipudi

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as continual learning entails memory and computational overhead. Crossbar architectures using memristor …

us (code pays fourni par la source)

5 citations Scientific Reports
Accès ouvert 2024 preprint OpenAlex

Probabilistic Metaplasticity for Continual Learning with Memristors

Fatima Tuz Zohora, Vedant Karia, Nicholas Soures, Dhireesha Kudithipudi

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as continual learning entails memory and computational overhead. Crossbar architectures using memristor …

0 citations arXiv (Cornell University)
2023 article OpenAlex

Two Decades of Poverty Reduction Politics in Canada: Better for Single-Parent Families and Single Working-Age Adults?

Geranda Notten, Fatima Tuz Zohora, Charles Plante, Rachel Laforest

Réduire la pauvreté est une tâche complexe. Nous cherchons à savoir si la situation des familles monoparentales et des adultes célibataires en âge de travailler s’est améliorée, dans un contexte politique qui priorise, du moins sur le plan rhétorique, la réduction de …

ca (code pays fourni par la source)

4 citations Canadian Public Policy
Accès ouvert 2023 article OpenAlex

Optimal site selection for solar plant using analytical hierarchy process ( AHP ): A case study in Bangladesh

Anjuman Ara, Fatima Tuz Zohora, Nabila Nurul, Anzum Tanvir et autres

Abstract Solar energy is one of the sources of renewable energy which is clean, affordable, and limitless. Despite Bangladesh having a significant potential for solar energy for its excellent geographic location, relatively low research work on location selection for the establishment of …

bd (code pays fourni par la source)

15 citations Environmental Progress & Sustainable Energy

BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.